The handling of nonresponse error

This study was designed to describe and explore how nonresponse in Human Resource DevelopmentQuarterly (HRDQ) historically has been handled. All feature and article manuscripts (n= 158) published in HRDQ during the years 1990 through 1999 were analyzed usingcontent analysis techniques. Study findings show that not mentioning nonresponse error as a threat to externalvalidity of a study, not attempting to control for nonresponse error, or not providing a reference to theliterature were unfortunately the norm and not the exception. Four recommendations for handling nonresponseerror are comparison of early to late respondents, using “days to respond” as a regressionvariable, comparing respondents to nonrespondents, and comparing respondents on characteristics known apriori.